US11294995B2ActiveUtilityA1

Method and apparatus for identity authentication, and computer readable storage medium

Assignee: BEIJING BAIDU NETCOM SCI & TECH CO LTDPriority: Jul 12, 2018Filed: Jul 10, 2019Granted: Apr 5, 2022
Est. expiryJul 12, 2038(~12 yrs left)· nominal 20-yr term from priority
Inventors:Runqi Zhang
G10L 17/22G06F 21/32G06F 3/16G10L 17/00
36
PatentIndex Score
0
Cited by
44
References
11
Claims

Abstract

Embodiments of the present disclosure relate to a method and an apparatus for identity authentication, an electronic device, and a computer readable storage medium. The method for identity authentication includes: acquiring a signal of a speech of a user; generating feature data with a plurality of dimensions based on the signal, the feature data with the plurality of dimensions indicate different characteristics of the signal; and determining an identity of the user based on the feature data.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
       1. A method for identity authentication, comprising:
 acquiring a signal of a speech of a user; 
 generating feature data with a plurality of dimensions based on the signal, the feature data with the plurality of dimensions indicating different characteristics of the signal; and 
 determining an identity of the user based on the feature data; 
 wherein determining the identity of the user comprises: 
 determining a number of sentences associated with a predefined identity and comprised in the signal; and 
 in response to a ratio of the number determined to a total number of sentences comprised in the signal greater than a threshold ratio, determining the identity of the user as the predefined identity. 
 
     
     
       2. The method according to  claim 1 , wherein the plurality of dimensions comprise at least two of:
 speed, loudness, pitch, frequency, and timbre. 
 
     
     
       3. The method according to  claim 1 , wherein determining the identity of the user comprises:
 determining a category of the signal based on the feature data; 
 acquiring a correspondence between the category of the signal and the identity of the user; and 
 determining the identity of the user as the identity corresponding to the category based on the correspondence. 
 
     
     
       4. The method according to  claim 3 , wherein the category of the signal is determined by an unsupervised learning model. 
     
     
       5. The method according to  claim 1 , further comprising:
 determining a permission of the user based on the identity of the user; and 
 triggering a task matching the permission of the user to be executed. 
 
     
     
       6. An apparatus for identity authentication, comprising:
 one or more processors and a memory, wherein the one or more processors are configured to: 
 acquire a signal of a speech of a user; 
 generate feature data with a plurality of dimensions based on the signal, the feature data with the plurality of dimensions indicating different characteristics of the signal; and 
 determine an identity of the user based on the feature data; 
 wherein the one or more processors determine the identity of the user by performing acts of: 
 determining a number of sentences associated with a predefined identity and comprised in the signal; and 
 in response to a ratio of the number determined to a total number of sentences comprised in the signal greater than a threshold ratio, determining the identity of the user as the predefined identity. 
 
     
     
       7. The apparatus according to  claim 6 , wherein the plurality of dimensions comprise at least two of:
 speed, loudness, pitch, frequency, and timbre. 
 
     
     
       8. The apparatus according to  claim 6 , wherein the one or more processors determine the identity of the user by performing acts of:
 determining a category of the signal based on the feature data; 
 acquiring a correspondence between the category of the signal and the identity of the user; and 
 determining the identity of the user as the identity corresponding to the category based on the correspondence. 
 
     
     
       9. The apparatus according to  claim 8 , wherein the category of the signal is determined by an unsupervised learning model. 
     
     
       10. The apparatus according to  claim 6 , wherein the one or more processors are configured to:
 determine a permission of the user based on the identity of the user; and 
 trigger a task matching the permission of the user to be executed. 
 
     
     
       11. A computer readable storage medium, stored thereon with computer programs that, when executed by a processor, the processor is caused to perform a method for identity authentication, wherein the method comprises:
 acquiring a signal of a speech of a user; 
 generating feature data with a plurality of dimensions based on the signal, the feature data with the plurality of dimensions indicating different characteristics of the signal; and 
 determining an identity of the user based on the feature data; 
 wherein determining the identity of the user comprises: 
 determining a number of sentences associated with a predefined identity and comprised in the signal; and 
 
       in response to a ratio of the number determined to a total number of sentences comprised in the signal greater than a threshold ratio, determining the identity of the user as the predefined identity.

Join the waitlist — get patent alerts

Track US11294995B2 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.